Arvutiteaduse instituut
  1. Kursused
  2. 2020/21 kevad
  3. Arvutusliku neuroteaduse seminar (MTAT.03.292)
EN
Logi sisse

Arvutusliku neuroteaduse seminar 2020/21 kevad

  • Main
  • Process
  • Timetable
  • Tips

Timetable

You can book when to present from this sheet. You can book a time even if you didn't select or found a paper yet. The earlier you book the better you can manage your schedule.

This semester we will discuss the problem of modularity and compositionally in neural networks. The discussion will be based on a recent paper by Schmidhuber's lab: On the Binding Problem in Artificial Neural Networks

The binding problem: The inability of existing neural networks to dynamically and flexibly bind information that is distributed throughout the network.
by Greff, van Steenkiste & Schmidhuber.

11.02 Week 0 - Kick-off seminar
Introduction, organization of the seminar, questions.
presented by Oriol Corcoll

18.02 Week 1 - Sections 1 & 2: Introduction & the binding problem
presented by Aleksei Kopõlov
feedback | test

25.02 Week 2 - The Psychophysical Evidence for a Binding Problem in Human Vision & Feature binding, attention and object perception
presented by Rodion Krjutškov
feedback | test

4.03 Week 3 - Neuronal Synchrony: A Versatile Code for the Definition of Relations? & Synchrony Unbound: A Critical Evaluation of the Temporal Binding Hypothesis
presented by Tetiana Rabiichuk

4.03 Week 3 - Short introduction to these two papers
presented by Jaan Aru

11.03 Week 4 - Section 3: Representation
presented by Denys Kolomiiets
feedback | test

18.03 Week 5 - Curve Circuits
presented by Shumpei Morimoto
feedback | test

25.03 Week 6 - Understanding RL Vision
presented by Farid Hasanov
feedback | test

1.04 Week 7 - Section 4: Segregation
presented by Taavi Luik
feedback | test

8.04 Week 8 - A Theory of Perceptual Objects
presented by Joonas Puura
feedback | test

15.04 Week 9 - Symbolic Behaviour in Artificial Intelligence
presented by Kaspar Valk
feedback | test

22.04 Week 10 - Section 5: Composition
presented by Romet Aidla
feedback | test

29.04 Week 11 - Compositionality decomposed: how do neural networks generalise?
presented by Taavi Kivisik
feedback | test

6.05 Week 12 - The binding problem in transformers
presented by Tarun Khajuria
feedback | test

13.05 Week 13 - Sections 6, 7 & 8: Insights from related disciplines, Discussion & Conclusions
presented by Siyuan Gao
feedback | test

20.05 Week 14 - The structure of illusory conjunctions reveals hierarchical binding of multipart objects
presented by Behrad Moeini
feedback | test

27.05 Week 15 - The evolutionary origins of modularity
presented by Sabina Mammadova
feedback | test

03.06 Week 16 - Unbinding bound objects with drugs
presented by Kristjan Kaup

10.06 Week 17 - How to represent part-whole hierarchiesin a neural network
presented by Tetiana Rabiichuk
feedback | test

  • Arvutiteaduse instituut
  • Loodus- ja täppisteaduste valdkond
  • Tartu Ülikool
Tehniliste probleemide või küsimuste korral kirjuta:

Kursuse sisu ja korralduslike küsimustega pöörduge kursuse korraldajate poole.
Õppematerjalide varalised autoriõigused kuuluvad Tartu Ülikoolile. Õppematerjalide kasutamine on lubatud autoriõiguse seaduses ettenähtud teose vaba kasutamise eesmärkidel ja tingimustel. Õppematerjalide kasutamisel on kasutaja kohustatud viitama õppematerjalide autorile.
Õppematerjalide kasutamine muudel eesmärkidel on lubatud ainult Tartu Ülikooli eelneval kirjalikul nõusolekul.
Courses’i keskkonna kasutustingimused